Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →inbox-management
Ongoing Gmail inbox management via scheduled runs. Archives known noise, flags urgent items, drafts replies in-thread (never auto-sends), and catches stale follow-ups. Starts in flag-only mode — earns autonomy through a three-stage trust ladder.
Passed 7 of 16 test cases with the skill, and 2 of 16 without it.
and 6 more in the full report
7 fixed2 passed either way12 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
Run the urgent notification check. The inbox contains an unread message from state.tax.gov titled 'Final Notice: Tax Assessment Signature Required'.
| Checked | Without skill | With skill |
|---|---|---|
| Flags the message from state.tax.gov as an urgent item due to its regulatory domain and required signature. | Missed | Passed |
| Consolidates the alert into a single notification rather than sending multiple alerts. | Passed | Passed |
The instructions your model reads when the skill loads.
Companion to inbox-cleanup. Cleanup drains the backlog once. Management keeps the inbox clean on a schedule — archiving noise, flagging urgents, drafting replies, and catching stale follow-ups.
Runs as a scheduled task (via the schedule skill). Each run should be silent unless something is worth interrupting the user for.
Default posture: high recall on noise archiving, high precision on user interruption. Archive aggressively on known-safe patterns. Ping sparingly. Never auto-send a reply. When unsure, flag instead of archiving.
A single wrong archive of an important email kills trust. Earn autonomy in stages:
| Stage | Archive behavior | Draft behavior | Alerts |
|---|---|---|---|
| 0 — Flag-only (default) | Nothing archived. All archive calls use --dry-run. Summary shows what would be archived for user review. | Drafts created in-thread, listed in summary. | Urgent scan active. |
| 1 — Standard | Silent archive of known-safe categories only (calendar responses, no-reply, newsletters). Cold outreach still flagged. Batches > 1,000 ops auto-dry-run. | Drafts created in-thread, summarized per run. | Urgent scan active. |
| 2 — Aggressive | Above + cold outreach archived by LLM judgment (default archive, flag only when relevant to user). All ops logged for reversal. | Same as Stage 1. | Urgent scan active. |
Graduation requires the user to explicitly say "graduate me" or equivalent. Do not infer from silence.
Never auto-send a draft. No toggle for this rule.
Before anything else, explain what the user is opting into. Be direct:
"Here's what inbox management does: on a schedule you choose (e.g. every few hours on weekdays), I'll scan your inbox and take action based on a trust level you control.
Stage 0 (the default starting point): I watch but don't touch. I'll tell you what I would archive, show you draft replies I wrote, and flag urgent items — but I won't move or delete anything. This lasts until you explicitly tell me to graduate.
Stage 1 (you opt in): I silently archive obvious noise — calendar responses, no-reply senders, newsletters. Everything else is still flagged for your review.
Stage 2 (you opt in): I also archive cold outreach using my judgment. Higher autonomy, slightly higher risk of a wrong call.
test cases passed, vs 2 / 16 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.